© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16418
    Prev
    Next
    INDEX
    Explanations

    German "or"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ответствен
    0.25
    耷
    0.24
    对了
    0.23
    atot
    0.23
    phalodes
    0.23
    ilere
    0.23
     astronomer
    0.22
    urrection
    0.22
    ajemy
    0.22
     अनो
    0.22
    POSITIVE LOGITS
    6
    0.26
    both
    0.26
    一下
    0.25
    3
    0.24
    1
    0.24
    2
    0.23
    یسی
    0.22
     source
    0.22
    4
    0.21
     whistle
    0.21
    Activations Density 0.005%

    No Known Activations